Benchmarks for evaluating intent-based chatbots

Benchmarks for evaluating intent-based chatbots

Given the growing importance of bots in all aspects of our digital live (including in software engineering!) and the well-known challenges to test any type of NLP intensive bot, we could definitely use a series of de facto standard datasets to soundly evaluate and...
Testing challenges for NLP-intensive bots

Testing challenges for NLP-intensive bots

The success of Artificial Intelligence (AI) has sparked substantial interest in the software engineering (SE) field to improve AI scalability and quality [1]. AI applications face common challenges in their SE processes [2]. Among those, they are hard to specify [3],...